Microsoft.VisualBasic.DataMining.UMAP 5.0.9762.11310.

Namespaces 3 Types 23 Members 142

01 Namespaces

Microsoft.VisualBasic.DataMining.UMAP

The UMAP (uniform manifold approximation and projection) dimensionality reduction algorithm.

Type	Summary	Members
ABParams	Fit the a, b parameters for the differentiable curve that is used in the construction of the low dimensional fuzzy simplicial complex.	8
DefaultRandomGenerator		2
DistanceFunctions		8
EpochSchedule	The number-of-epochs heuristic that is used by the SGD optimization.	6
Heaps		11
NNDescent	UMAP (Uniform Manifold Approximation and Projection) is a nonlinear dimensionality reduction technique widely used in data science and machine learning to visualize high-dimension…	1
NNDescentFn		1
NNDescentLoop	implements NNDescent parallel loop	1
NumericTableExtensions	UMAP 降维算法的统一二维表入口。	1
OptimizationState		7
ParallelConfig	A unified parallelism configuration for the UMAP pipeline	9
RowCol		1
RPTree	In the context of the NNDescent algorithm, an rpTree (Random Projection Tree) is a data structure used to index high-dimensional data points for efficient nearest neighbor searc…	1
SgdEpochTask	implements the SGD optimization loop of one epoch in parallel	1
SparseMatrix		19
Umap	UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction	22
UMAPProject	binary file data model for save the UMAP embedding result	8
Utils		6

Microsoft.VisualBasic.DataMining.UMAP.KNN

K nearest neighbour search used by the UMAP algorithm.

Type	Summary	Members
KNearestNeighbour	K Nearest Neighbour Search Uses a kd-tree to find the p number of near neighbours for each point in an input/output dataset.	3
KNNArguments	the argument collection of the KNN search and the nearest neighbour descent procedure	17
KNNState	index and the distance matrix of the corresponding indexed entity	2
SmoothKNN		1

Microsoft.VisualBasic.DataMining.UMAP.Tree

Tree structures used by the UMAP algorithm.

Type	Summary	Members
Tree		6